def testLearnModel(self):
minSplit = 20
maxDepth = 3
gamma = 0.00
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit,
maxDepth=maxDepth,
gamma=gamma)
learner.learnModel(X, y)
tree = learner.getTree()
#Work out penalty cost
predY = learner.predict(X)
predTestY = learner.predict(testX)
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
error = (1 - gamma) * numpy.sum(predY != y) / n
testError = numpy.sum(predTestY != testY) / float(testY.shape[0])
error += gamma * numpy.sqrt(T)
self.assertEquals(error, learner.treeObjective(X, y))
#Check if the values in the tree nodes are correct
for vertexId in tree.getAllVertexIds():
vertex = tree.getVertex(vertexId)
self.assertTrue(vertex.getValue() == 1.0
or vertex.getValue() == -1.0)
if tree.isNonLeaf(vertexId):
self.assertTrue(0 <= vertex.getFeatureInd() <= X.shape[1])
self.assertTrue(0 <= vertex.getError() <= 1)
def testLearnModel(self):
minSplit = 20
maxDepth = 3
gamma = 0.00
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit, maxDepth=maxDepth, gamma=gamma)
learner.learnModel(X, y)
tree = learner.getTree()
#Work out penalty cost
predY = learner.predict(X)
predTestY = learner.predict(testX)
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
error = (1-gamma)*numpy.sum(predY!=y)/n
testError = numpy.sum(predTestY!=testY)/float(testY.shape[0])
error += gamma*numpy.sqrt(T)
self.assertEquals(error, learner.treeObjective(X, y))
#Check if the values in the tree nodes are correct
for vertexId in tree.getAllVertexIds():
vertex = tree.getVertex(vertexId)
self.assertTrue(vertex.getValue()==1.0 or vertex.getValue()==-1.0)
if tree.isNonLeaf(vertexId):
self.assertTrue(0 <= vertex.getFeatureInd() <= X.shape[1])
self.assertTrue(0 <= vertex.getError() <= 1)
def testComputeAlphas(self):
minSplit = 20
maxDepth = 3
gamma = 0.1
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit,
maxDepth=maxDepth,
gamma=gamma,
pruning=False)
learner.learnModel(X, y)
tree = learner.getTree()
rootId = (0, )
learner.tree.getVertex(rootId).setTestInds(numpy.arange(X.shape[0]))
learner.predict(X, y)
learner.computeAlphas()
#See if the alpha values of the nodes are correct
for vertexId in tree.getAllVertexIds():
subtreeLeaves = tree.leaves(vertexId)
subtreeError = 0
for subtreeLeaf in subtreeLeaves:
subtreeError += (
1 - gamma) * tree.getVertex(subtreeLeaf).getTestError()
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
subtreeError /= n
subtreeError += gamma * numpy.sqrt(T)
T2 = T - len(tree.subtreeIds(vertexId)) + 1
vertexError = (1 -
gamma) * tree.getVertex(vertexId).getTestError() / n
vertexError += gamma * numpy.sqrt(T2)
self.assertAlmostEquals((subtreeError - vertexError),
tree.getVertex(vertexId).alpha)
if tree.isLeaf(vertexId):
self.assertEquals(tree.getVertex(vertexId).alpha, 0.0)
#Let's check the alpha of the root node via another method
rootId = (0, )
T = 1
(n, d) = X.shape
n = float(n)
vertexError = (1 - gamma) * numpy.sum(y != Util.mode(y)) / n
pen = gamma * numpy.sqrt(T)
vertexError += pen
T = tree.getNumVertices()
treeError = (1 - gamma) * numpy.sum(y != learner.predict(X)) / n
pen = gamma * numpy.sqrt(T)
treeError += pen
alpha = treeError - vertexError
self.assertAlmostEqual(alpha, tree.getVertex(rootId).alpha)
def testComputeAlphas(self):
minSplit = 20
maxDepth = 3
gamma = 0.1
X, y = self.X, self.y
testX = X[100:, :]
testY = y[100:]
X = X[0:100, :]
y = y[0:100]
learner = PenaltyDecisionTree(minSplit=minSplit, maxDepth=maxDepth, gamma=gamma, pruning=False)
learner.learnModel(X, y)
tree = learner.getTree()
rootId = (0,)
learner.tree.getVertex(rootId).setTestInds(numpy.arange(X.shape[0]))
learner.predict(X, y)
learner.computeAlphas()
#See if the alpha values of the nodes are correct
for vertexId in tree.getAllVertexIds():
subtreeLeaves = tree.leaves(vertexId)
subtreeError = 0
for subtreeLeaf in subtreeLeaves:
subtreeError += (1-gamma)*tree.getVertex(subtreeLeaf).getTestError()
n = float(X.shape[0])
d = X.shape[1]
T = tree.getNumVertices()
subtreeError /= n
subtreeError += gamma * numpy.sqrt(T)
T2 = T - len(tree.subtreeIds(vertexId)) + 1
vertexError = (1-gamma)*tree.getVertex(vertexId).getTestError()/n
vertexError += gamma * numpy.sqrt(T2)
self.assertAlmostEquals((subtreeError - vertexError), tree.getVertex(vertexId).alpha)
if tree.isLeaf(vertexId):
self.assertEquals(tree.getVertex(vertexId).alpha, 0.0)
#Let's check the alpha of the root node via another method
rootId = (0,)
T = 1
(n, d) = X.shape
n = float(n)
vertexError = (1-gamma)*numpy.sum(y != Util.mode(y))/n
pen = gamma*numpy.sqrt(T)
vertexError += pen
T = tree.getNumVertices()
treeError = (1-gamma)*numpy.sum(y != learner.predict(X))/n
pen = gamma*numpy.sqrt(T)
treeError += pen
alpha = treeError - vertexError
self.assertAlmostEqual(alpha, tree.getVertex(rootId).alpha)
